RDMA/rxe: Implement memory access through MWs

Add code to implement memory access through memory windows.

Link: https://lore.kernel.org/r/20210608042552.33275-10-rpearsonhpe@gmail.com
Signed-off-by: Bob Pearson <rpearsonhpe@gmail.com>
Signed-off-by: Jason Gunthorpe <jgg@nvidia.com>

drivers/infiniband/sw/rxe/rxe_loc.h

@@ -94,6 +94,7 @@ int rxe_alloc_mw(struct ib_mw *ibmw, struct ib_udata *udata);
 int rxe_dealloc_mw(struct ib_mw *ibmw);
 int rxe_bind_mw(struct rxe_qp *qp, struct rxe_send_wqe *wqe);
 int rxe_invalidate_mw(struct rxe_qp *qp, u32 rkey);
+struct rxe_mw *rxe_lookup_mw(struct rxe_qp *qp, int access, u32 rkey);
 void rxe_mw_cleanup(struct rxe_pool_entry *arg);
 
 /* rxe_net.c */

drivers/infiniband/sw/rxe/rxe_mw.c

@@ -312,6 +312,29 @@ int rxe_invalidate_mw(struct rxe_qp *qp, u32 rkey)
 	return ret;
 }
 
+struct rxe_mw *rxe_lookup_mw(struct rxe_qp *qp, int access, u32 rkey)
+{
+	struct rxe_dev *rxe = to_rdev(qp->ibqp.device);
+	struct rxe_pd *pd = to_rpd(qp->ibqp.pd);
+	struct rxe_mw *mw;
+	int index = rkey >> 8;
+
+	mw = rxe_pool_get_index(&rxe->mw_pool, index);
+	if (!mw)
+		return NULL;
+
+	if (unlikely((rxe_mw_rkey(mw) != rkey) || rxe_mw_pd(mw) != pd ||
+		     (mw->ibmw.type == IB_MW_TYPE_2 && mw->qp != qp) ||
+		     (mw->length == 0) ||
+		     (access && !(access & mw->access)) ||
+		     mw->state != RXE_MW_STATE_VALID)) {
+		rxe_drop_ref(mw);
+		return NULL;
+	}
+
+	return mw;
+}
+
 void rxe_mw_cleanup(struct rxe_pool_entry *elem)
 {
 	struct rxe_mw *mw = container_of(elem, typeof(*mw), pelem);

drivers/infiniband/sw/rxe/rxe_resp.c

@@ -413,6 +413,7 @@ static enum resp_states check_rkey(struct rxe_qp *qp,
 				   struct rxe_pkt_info *pkt)
 {
 	struct rxe_mr *mr = NULL;
+	struct rxe_mw *mw = NULL;
 	u64 va;
 	u32 rkey;
 	u32 resid;
@@ -424,6 +425,7 @@ static enum resp_states check_rkey(struct rxe_qp *qp,
 	if (pkt->mask & (RXE_READ_MASK | RXE_WRITE_MASK)) {
 		if (pkt->mask & RXE_RETH_MASK) {
 			qp->resp.va = reth_va(pkt);
+			qp->resp.offset = 0;
 			qp->resp.rkey = reth_rkey(pkt);
 			qp->resp.resid = reth_len(pkt);
 			qp->resp.length = reth_len(pkt);
@@ -432,6 +434,7 @@ static enum resp_states check_rkey(struct rxe_qp *qp,
 						     : IB_ACCESS_REMOTE_WRITE;
 	} else if (pkt->mask & RXE_ATOMIC_MASK) {
 		qp->resp.va = atmeth_va(pkt);
+		qp->resp.offset = 0;
 		qp->resp.rkey = atmeth_rkey(pkt);
 		qp->resp.resid = sizeof(u64);
 		access = IB_ACCESS_REMOTE_ATOMIC;
@@ -451,18 +454,36 @@ static enum resp_states check_rkey(struct rxe_qp *qp,
 	resid	= qp->resp.resid;
 	pktlen	= payload_size(pkt);
 
-	mr = lookup_mr(qp->pd, access, rkey, RXE_LOOKUP_REMOTE);
+	if (rkey_is_mw(rkey)) {
-	if (!mr) {
+		mw = rxe_lookup_mw(qp, access, rkey);
-		state = RESPST_ERR_RKEY_VIOLATION;
+		if (!mw) {
-		goto err;
+			pr_err("%s: no MW matches rkey %#x\n", __func__, rkey);
+			state = RESPST_ERR_RKEY_VIOLATION;
+			goto err;
+		}
+
+		mr = mw->mr;
+		if (!mr) {
+			pr_err("%s: MW doesn't have an MR\n", __func__);
+			state = RESPST_ERR_RKEY_VIOLATION;
+			goto err;
+		}
+
+		if (mw->access & IB_ZERO_BASED)
+			qp->resp.offset = mw->addr;
+
+		rxe_drop_ref(mw);
+		rxe_add_ref(mr);
+	} else {
+		mr = lookup_mr(qp->pd, access, rkey, RXE_LOOKUP_REMOTE);
+		if (!mr) {
+			pr_err("%s: no MR matches rkey %#x\n", __func__, rkey);
+			state = RESPST_ERR_RKEY_VIOLATION;
+			goto err;
+		}
 	}
 
-	if (unlikely(mr->state == RXE_MR_STATE_FREE)) {
+	if (mr_check_range(mr, va + qp->resp.offset, resid)) {
-		state = RESPST_ERR_RKEY_VIOLATION;
-		goto err;
-	}
-
-	if (mr_check_range(mr, va, resid)) {
 		state = RESPST_ERR_RKEY_VIOLATION;
 		goto err;
 	}
@@ -496,6 +517,9 @@ static enum resp_states check_rkey(struct rxe_qp *qp,
 err:
 	if (mr)
 		rxe_drop_ref(mr);
+	if (mw)
+		rxe_drop_ref(mw);
+
 	return state;
 }
 
@@ -520,8 +544,8 @@ static enum resp_states write_data_in(struct rxe_qp *qp,
 	int	err;
 	int data_len = payload_size(pkt);
 
-	err = rxe_mr_copy(qp->resp.mr, qp->resp.va, payload_addr(pkt), data_len,
+	err = rxe_mr_copy(qp->resp.mr, qp->resp.va + qp->resp.offset,
-			  RXE_TO_MR_OBJ, NULL);
+			  payload_addr(pkt), data_len, RXE_TO_MR_OBJ, NULL);
 	if (err) {
 		rc = RESPST_ERR_RKEY_VIOLATION;
 		goto out;
@@ -540,7 +564,6 @@ static DEFINE_SPINLOCK(atomic_ops_lock);
 static enum resp_states process_atomic(struct rxe_qp *qp,
 				       struct rxe_pkt_info *pkt)
 {
-	u64 iova = atmeth_va(pkt);
 	u64 *vaddr;
 	enum resp_states ret;
 	struct rxe_mr *mr = qp->resp.mr;
@@ -550,7 +573,7 @@ static enum resp_states process_atomic(struct rxe_qp *qp,
 		goto out;
 	}
 
-	vaddr = iova_to_vaddr(mr, iova, sizeof(u64));
+	vaddr = iova_to_vaddr(mr, qp->resp.va + qp->resp.offset, sizeof(u64));
 
 	/* check vaddr is 8 bytes aligned. */
 	if (!vaddr || (uintptr_t)vaddr & 7) {
@@ -674,8 +697,10 @@ static enum resp_states read_reply(struct rxe_qp *qp,
 		res->type		= RXE_READ_MASK;
 		res->replay		= 0;
 
-		res->read.va		= qp->resp.va;
+		res->read.va		= qp->resp.va +
-		res->read.va_org	= qp->resp.va;
+					  qp->resp.offset;
+		res->read.va_org	= qp->resp.va +
+					  qp->resp.offset;
 
 		res->first_psn		= req_pkt->psn;
 

drivers/infiniband/sw/rxe/rxe_verbs.h

@@ -186,6 +186,7 @@ struct rxe_resp_info {
 
 	/* RDMA read / atomic only */
 	u64			va;
+	u64			offset;
 	struct rxe_mr		*mr;
 	u32			resid;
 	u32			rkey;
@@ -483,6 +484,16 @@ static inline u32 mr_rkey(struct rxe_mr *mr)
 	return mr->ibmr.rkey;
 }
 
+static inline struct rxe_pd *rxe_mw_pd(struct rxe_mw *mw)
+{
+	return to_rpd(mw->ibmw.pd);
+}
+
+static inline u32 rxe_mw_rkey(struct rxe_mw *mw)
+{
+	return mw->ibmw.rkey;
+}
+
 int rxe_register_device(struct rxe_dev *rxe, const char *ibdev_name);
 
 void rxe_mc_cleanup(struct rxe_pool_entry *arg);